Security audit

每日情报自动化系统

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent, but it directs recurring autonomous briefing delivery through external services without enough scoping, consent, or removal controls.

Review before installing. Use this only in a constrained workspace with least-privilege Feishu/Lark and messaging credentials, confirm recipients before any send, prefer one-time preview runs first, and create scheduled cron jobs only with an explicit expiration and a documented removal process.

A.I.G

Vulnerability Patterns

System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review

Findings (2)

T06 · System Persistence

Error

Location: SKILL.md:76
Finding: Persistent Autonomous Execution Through Scheduled Agent Tasks
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:8
Finding: Unpinned Third-Party Dependencies and Browser Components
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description emphasizes automation and delivery but does not give a prominent warning that generated content may be uploaded to external services and sent to recipients. In context, this omission is material because the skill integrates with Feishu/Lark, voice generation, and cron scheduling, so users may invoke it expecting local content generation rather than external publication or recurring delivery.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The quick-start phrase is a natural-language request that could plausibly appear in ordinary conversation, making accidental invocation more likely. In this skill, accidental triggering is more dangerous than usual because execution can search external sources, generate content, and deliver outputs through Feishu/Lark with limited explicit warning at invocation time.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The second example is similarly broad and describes a common content-creation task without any constraint tying it to deliberate skill invocation. Because this skill can produce and distribute generated artifacts automatically, an ambiguous trigger increases the risk of unintentional execution, data egress, or message delivery to configured recipients.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.